fixed

Author: sunxiaojian

pyiceberg/types.py

@@ -47,6 +47,7 @@
     Field,
     PrivateAttr,
     SerializeAsAny,
+    field_validator,
     model_serializer,
     model_validator,
 )
@@ -310,6 +311,14 @@ class NestedField(IcebergType):
         ...     doc="Just a long"
         ... ))
         '2: bar: required long (Just a long)'
+        >>> str(NestedField(
+        ...     field_id=3,
+        ...     name='baz',
+        ...     field_type="string",
+        ...     required=True,
+        ...     doc="A string field"
+        ... ))
+        '3: baz: required string (A string field)'
     """
 
     field_id: int = Field(alias="id")
@@ -320,6 +329,16 @@ class NestedField(IcebergType):
     initial_default: Optional[Any] = Field(alias="initial-default", default=None, repr=False)
     write_default: Optional[L] = Field(alias="write-default", default=None, repr=False)  # type: ignore
 
+    @field_validator("field_type", mode="before")
+    def convert_field_type(cls, v: Any) -> IcebergType:
+        """Convert string values into IcebergType instances."""
+        if isinstance(v, str):
+            try:
+                return IcebergType.handle_primitive_type(v, None)
+            except ValueError as e:
+                raise ValueError(f"Unsupported field type: '{v}'") from e
+        return v
+
     def __init__(
         self,
         field_id: Optional[int] = None,
@@ -340,12 +359,6 @@ def __init__(
         data["doc"] = doc
         data["initial-default"] = data["initial-default"] if "initial-default" in data else initial_default
         data["write-default"] = data["write-default"] if "write-default" in data else write_default
-        if isinstance(data["type"], str):
-            try:
-                data["type"] = IcebergType.handle_primitive_type(data["type"], None)
-            except ValueError as e:
-                raise ValueError(f"Unsupported field type: {data['type']}.") from e
-
         super().__init__(**data)
 
     def __str__(self) -> str:

tests/test_types.py

@@ -62,6 +62,21 @@
     (12, BinaryType),
 ]
 
+primitive_types = {
+    "boolean": BooleanType,
+    "int": IntegerType,
+    "long": LongType,
+    "float": FloatType,
+    "double": DoubleType,
+    "date": DateType,
+    "time": TimeType,
+    "timestamp": TimestampType,
+    "timestamptz": TimestamptzType,
+    "string": StringType,
+    "uuid": UUIDType,
+    "binary": BinaryType,
+}
+
 
 @pytest.mark.parametrize("input_index, input_type", non_parameterized_types)
 def test_repr_primitive_types(input_index: int, input_type: Type[PrimitiveType]) -> None:
@@ -232,19 +247,24 @@ def test_nested_field() -> None:
 
 
 def test_nested_field_type_as_str_unsupported() -> None:
-    with pytest.raises(ValueError) as exc_info:
-        _ = (NestedField(1, "field", "list", required=True),)
-    assert "Unsupported field type: list" in str(exc_info.value)
+    unsupported_types = ["list", "map", "struct"]
+    for type_str in unsupported_types:
+        with pytest.raises(ValueError) as exc_info:
+            _ = NestedField(1, "field", type_str, required=True)
+        assert f"Unsupported field type: '{type_str}'" in str(exc_info.value)
 
 
-def test_nested_field_type_as_str_struct() -> None:
+@pytest.mark.parametrize("type_str, type_class", primitive_types.items())
+def test_nested_field_type_as_str(type_str: str, type_class: type) -> None:
     field_var = NestedField(
         1,
         "field",
-        "string",
+        type_str,
         required=True,
     )
-    assert isinstance(field_var.field_type, StringType)
+    assert isinstance(
+        field_var.field_type, type_class
+    ), f"Expected {type_class.__name__}, got {field_var.field_type.__class__.__name__}"
 
 
 @pytest.mark.parametrize("input_index,input_type", non_parameterized_types)